Describing location in distributions

advertisement
Chapter 3 Notes: Examining Relationships
Answers
1. What is the difference between a response variable and an explanatory variable?
The explanatory variable is your x variable. It is the variable that you are using to predict you y or
response variable.
2. How are response and explanatory variables related to dependent and independent variable?
Your prediction for the response variable depends on what your independent or explanatory
variable is.
3. When is it appropriate to use a scatterplot to display data?
When you have two groups of quantitative data.
4. Which variable always appears on the horizontal axis of a scatterplot?
Explanatory variable
5. You can describe the overall pattern of a scatterplot by the ….
Strength, Direction, and Form
6. Explain the difference between a positive association and a negative association.
Two variables are positively associated when above-average values of one tend to accompany
above-average values of the other and below-average values also tend to occur together.
Two variables are negatively associated when above-average values of one tend to accompany
below-average values of the other, and vice versa.
7. How can quantitative data which belongs to different categories be differentiated on a scatterplot?
Use different colors for the points.
8. What does correlation measure?
Correlation measures how well the data can be modeled by a linear relationship.
9. Explain why two variables must both be quantitative in order to find the correlation between
them.
Because the formula requires a standard deviation and mean for both variables, and categorical
data does not have a measure of spread and center.
10. What is true about the relationship between two variables if the relationship is:
a) Near 0? No linear relationship
b) Near 1? The relationship is positive and could almost be perfectly be modeled by a line.
c) Near -1? Negative
d) Exactly 1? All the points would fall exactly on a line with positive slope
e) Exactly -1? All the points would fall exactly on a line with negative slope
11. Is correlation resistant to extreme observations?
No. Outliers can greatly change the value of r.
12. What does it mean if two variables have high correlation? It means that one the explanatory
variable does a very good job of predicting what the response variable would be. The relationship
follows a linear model very well and we can use a linear equation to make predictions about what
the response variable could be based on a given explanatory.
13. What does it mean if two variables have weak correlation?
A linear model does not do a very good job of explain the relationship between the two variables.
14. What does it mean if two variables have no correlation?
A linear model would be useless for describing the relationship.
3.2 Least-Squares Regression (pp. 199-233)
1. In what way is a regression line a mathematical model?
It describes how a response variable y changes as an explanatory variable x
changes. A regression line can be used to predict the value of y for a given
value of x.
2. What is extrapolation and why is this dangerous?
Extrapolation is predicting a y value by extending the regression model to regions outside the
range of the x-values of the data. It’s dangerous because it introduces the questionable and
untested assumption that the relationship between x and y does not change.
3. What is a least-squares regression line?
A least-squares regression line is a regression line that minimizes the sum of the squares of the residuals
(the vertical distances of the data points from the line)
4. What is the formula for the equation of the least-squares regression line?
5. The least-squares regression line always passes through the point…
The grand mean
6. What is a residual?
A residual is the difference between an observed value of the response variable and the value predicted
by the regression line. observed y – predicted y
7. How can you calculate residuals on your calculator and use this to produce a residual plot?
To calculate residuals on your calculator: With data in Lists 1 and 2, enter y hat in highlighted L3
but replace the x in y hat with (L1) and press enter. Next with L4 highlighted, enter L2 minus L3
and press enter to see the residuals displayed in L4. To produce a residual plot: Create (turn on) a
plot with L1 as the x variable and L4 as the y variable. Use ZOOM 9 to see the residual plot. NOTE:
To compute the standard deviation of the residuals, calculate a 1-VAR STAT on the residual list.
8. If a least-squares regression line fits the data well, what characteristics should the residual plot exhibit?
Residual plots help us assess how well a regression line fits the data. If the points in a residual
plot are randomly dispersed around the horizontal axis, then a linear regression model is
appropriate for the data; otherwise a non-linear model is appropriate.
Chapter 3 Notes: Examining Relationships
9. How is the coefficient of determination defined?
As r2 – which is the square of the correlation coefficient, r. The coefficient of determination is equal to
the percent of variation in one variable that is accounted for (predicted) by the other variable.
10. What is the formula for calculating the coefficient of determination?
11.
Find r:
Then square the answer….DONE ON YOUR CALCULATOR!
12. if r2 = 0.95, what can be concluded about the relationship between x and y?
95% of the variation in y is explained by the linear model relating y to x. Remember, r2 is a
reported measure of how successful the regression model was in explaining the response variable.
3.3 Correlation and Regression Wisdom (pp. 233-251)
1. What are three limitations of correlation and regression?
1. The distinction between explanatory and response variables is important in regression; reversing x
and y will yield a different least-squares regression line.
2). Correlation and regression lines describe only linear relationships.
3). Correlation and least-squares regression lines are not resistant.
2. Under what conditions does an outlier become an influential observation?
An observation is influential for a statistical calculation if removing it noticeably changes the result of
the calculation. Points that are outliers in the x direction of a scatterplot are often influential for the
least-squares regression line. Influential points often have small residuals, because they pull the
regression line toward themselves.
3. What is a lurking variable?
A hidden variable in a study, research, experiment, etc. that may affect the predictor variables given.
In other words, a lurking variable is not among the explanatory or response variables in a study, but it
may influence the variation in the response variable.
4. Why does association not imply causation?
A strong association between two variables is not enough evidence to draw conclusions about cause
and effect.
Download